A pytorch implementation of MCDO(Monte-Carlo Dropout methods)

Uncertainty Estimation Using Deep Neural Network and Gradient Boosting Methods

All the material needed to use MC-CP and the Adaptive MC Dropout method

Bayesian deep learning experiments

An experimental Python package for learning Bayesian Neural Network.

An NLP Model used for automated assignment of bug reports to the relevant engineering team. Utilizes a novel confidence bounding approach - Monte Carlo Dropout, and assigns underconfident predictions to a queue for human review. Built for Pegasystems Inc.

PyTorch implementation of landmark-based facial expression recognition using Spatio-Temporal BiLinear Networks (ST-BLN)

(Forked Version) Experiments used in "Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning"

Comparison of a network implemented via Variational Inference with the same network implemented via Monte Carlo Dropout

Probabilistic approach to neural nets - modern scalable approximate inference methods

Analyzing deep learning models with uncertainty in predictions

A Deep Learning Neural Network that classifies Vector Like Quarks from background events using generated collider data

Epistemic uncertainty, sometimes referred to as model uncertainty, describes what the model does not know because training data was not appropriate. Modelling epistemic uncertainty is crucial to prevent ill advised discussion making due to over confident models.

🤔 Methods for measuring and visualising the uncertainty in neural networks